def dictor(breed, cdfs):
breed_dict = {}
name_dict = {}
b_list = []
for i in cdfs:
if str(breed) in str(i):
b_list.append(i)
for ber in b_list:
a = ber.split('-')
print('a=', a)
b = list(a)
#print a
print('b[1]=', b[1])
if b[1] in breed_dict:
expr = load_expr(ber)
name_dict[b[1]].append(ber)
breed_dict[b[1]].append(expr)
else:
expr = load_expr(ber)
name_dict[b[1]] = [ber]
breed_dict[b[1]] = [expr]
#print breed_dict
return breed_dict, name_dict
def rep_dict(cdfs):
"""
@summary: Creates two dictionaries, one consisting of the experiment names, ordered by ID number
the second consisting of the sample names, ordered by ID number as well.
These dictionaries allow for the replicate grouping alignment.
@param cdfs: List of .expr files to be aligned with each other
@return: Breed_dict[], dictionary containing loaded experiments
@return: name_dict[], dictionary containing sample name associated to experiment files
"""
breed_dict = {}
name_dict = {}
for i in cdfs:
a = i.split('-')
print(a)
b = list(a)
# print a
c = (b[3]).split('_')
if c[0] in breed_dict:
expr = load_expr(i)
name_dict[c[0]].append(i)
breed_dict[c[0]].append(expr)
else:
expr = load_expr(i)
name_dict[c[0]] = [i]
breed_dict[c[0]] = [expr]
print(breed_dict)
return breed_dict, name_dict
def alifeGuru(listem, folder_expr):
# within replicates alignment parameters
Dw = 2.0 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
trees = []
expr_list = []
expr_dir = folder_expr
for gru_list in listem:
for item in gru_list:
print('Aligning...' + item)
file_name = os.path.join(expr_dir, item)
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
print('F1' + '\n')
print(F1)
trees.append(F1)
for t in trees:
T1 = PairwiseAlignment(t, Dw, Gw)
print('T1' + '\n')
print(T1)
A1 = align_with_tree(T1, min_peaks=2)
A1.write_csv(
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/fullSpec_rt.csv',
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/fullSpec_area.csv'
)
print(trees)
def main():
folder_exprs = '/home/juicebox/Desktop/StrawberryExotic/parameters_v/bigFold'
llamas = [
'Alexandria', 'Bucharica', 'Capron', 'Tortona', 'Mara', 'Mignonette',
'Strawberry', 'Viridis'
]
listem = []
bigF = []
for name in llamas:
nomo = '*' + name + '*' + '.cdf.expr'
print('nomo=', nomo)
list_of_expr, names = glob(glob_pattern=nomo,
directoryname=folder_exprs)
print('LoE=', list_of_expr)
print('name=', name)
listem.append(list_of_expr)
for var in listem:
print(var)
expr_loaded = []
for straw in var:
expr = load_expr(straw)
expr_loaded.append(expr)
print(len(expr_loaded))
bigF.append(expr_loaded)
print('bigF=', bigF)
aligner(bigF)
print('Done!')
def load_expr_list_from_runlist(runs):
el = []
for run in runs:
file_name = os.path.join(expr_dir, run + ".expr")
expr = load_expr(file_name)
el.append(expr)
return el
def load_expr_list_from_runlist(runs):
el = []
for run in runs:
file_name = os.path.join(expr_dir, run + ".expr")
expr = load_expr(file_name)
el.append(expr)
return el
def load_expr_list():
# loads expr list from a directory of exprs
global exprdir
el = []
for file in glob.glob(os.path.join(exprdir, '*.expr')):
print file
expr = load_expr(file)
el.append(expr)
return el
def load_expr_list():
# loads expr list from a directory of exprs
global exprdir
el = []
for file in glob.glob( os.path.join(exprdir, '*.expr') ):
print file
expr = load_expr(file)
el.append(expr)
return el
def lil_dictor(cdfs):
breed_dict = {}
name_dict = {}
for i in cdfs:
a = i.split('-')
print(a)
b = list(a)
#print a
print(b[1])
if b[1] in breed_dict:
expr = load_expr(i)
name_dict[b[1]].append(i)
breed_dict[b[1]].append(expr)
else:
expr = load_expr(i)
name_dict[b[1]] = [i]
breed_dict[b[1]] = [expr]
print(breed_dict)
return breed_dict, name_dict
def alife(exprZ, folder_expr):
# within replicates alignment parameters
Dw = 10.0 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
expr_list = []
expr_dir = folder_expr
for expr_code in exprZ:
print('Aligning...' + expr_code)
file_name = os.path.join(expr_dir, expr_code)
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
print('F1' + '\n')
print(F1)
T1 = PairwiseAlignment(F1, Dw, Gw)
print('T1' + '\n')
print(T1)
A1 = align_with_tree(T1, min_peaks=2)
A1.write_csv(
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/Allstar10_rt.csv',
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/Allstar10_area.csv'
)
# default, float masses with interval (bin interval) of one from min mass
print "default intensity matrix, bin interval = 1, boundary +/- 0.5"
im = build_intensity_matrix(data)
im.null_mass(73)
im.null_mass(147)
n_scan, n_mz = im.get_size()
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
# Load the experiment
exper = load_expr(expr_file)
# Load the peak list
peak_list = exper.get_peak_list()
# Pass Ion Chromatograms into a list of ICs
n_mz = len(im.get_mass_list())
ic = []
for m in range(n_mz):
ic.append(im.get_ic_at_index(m))
# Create a new display object, this time plot four ICs
# and the TIC, as well as the peak list
display = Display()
# define the input experiments list
exprA_codes = ["a0806_077", "a0806_078", "a0806_079"]
exprB_codes = ["a0806_140", "a0806_141", "a0806_142"]
# within replicates alignment parameters
Dw = 2.5 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
print 'Aligning expt A'
expr_list = []
expr_dir = "../61a/output/"
for expr_code in exprA_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=2)
top_ion_list = A1.common_ion()
A1.write_common_ion_csv('output/area2.csv', top_ion_list)
print 'Aligning expt B'
expr_list = []
expr_dir = "../61b/output/"
for expr_code in exprB_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
def main():
parser = argparse.ArgumentParser(
description=
"Pre-processing & Peak detection tool for GC-MS .cdf formatted data")
parser.add_argument(
"-e",
action="store",
dest="exprDir",
nargs="?",
type=str,
default="/workdir2/cpowell/rasp2018/",
help="Location of .expr files to be aligned; Default= '/tmp/' ")
parser.add_argument(
"-o",
action="store",
dest="opDir",
nargs="?",
type=str,
default="/tmp/",
help="location to store the alignment .csv output file",
)
parser.add_argument(
"-m",
action="store",
nargs="?",
const=1,
type=float,
default=2.5,
help=
"Modulation time allowed between peaks considered similar; Default=2.5",
dest="mod",
)
parser.add_argument(
"-g",
action="store",
nargs="?",
const=1,
type=float,
default=0.30,
help="Gap penalty; Default=0.30",
dest="gap",
)
parser.add_argument(
"-p",
action="store",
nargs="?",
const=1,
type=int,
default=2,
help=
"Minimum number of peaks pre sample required for alignment ; Default=2",
dest="minPeak",
)
parser.add_argument(
"-n",
action="store",
nargs="?",
type=str,
default="alignment",
help=
"Number of points used to determine window size for peak detection; Default='alignment'",
dest="nameTag",
)
args = parser.parse_args()
print(args)
#folder_with_exprs = sys.argv[1]
#align_dir = sys.argv[2]
#mod = sys.argv[3]
#gp = sys.argv[4]
expr_loaded = []
list_of_exprs, names = glob(glob_pattern='*.expr',
directoryname=args.exprDir)
for i in list_of_exprs:
print(i)
expr = load_expr(i)
expr_loaded.append(expr)
singleAlign(expr_loaded, args.opDir, args.mod, args.gap, args.minPeak,
args.nameTag)
print('Done!')
# define the input experiments list
exprA_codes = [ "a0806_077", "a0806_078", "a0806_079" ]
exprB_codes = [ "a0806_140", "a0806_141", "a0806_142" ]
# within replicates alignment parameters
Dw = 2.5 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
print 'Aligning expt A'
expr_list = []
expr_dir = "../61a/output/"
for expr_code in exprA_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=2)
top_ion_list = A1.common_ion()
A1.write_common_ion_csv('output/area2.csv', top_ion_list)
print 'Aligning expt B'
expr_list = []
expr_dir = "../61b/output/"
for expr_code in exprB_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
def main():
parser = argparse.ArgumentParser(
description=
"Peak alignment tool with adjustable tolerances & grouping strategies")
parser.add_argument(
"-e",
action="store",
dest="exprDir",
nargs="?",
type=str,
default="/workdir2/cpowell/rasp2018/",
help=
"Location of .expr files to be aligned; Default= '/workdir2/cpowell/rasp2018/' "
)
parser.add_argument(
"-o",
action="store",
dest="opDir",
nargs="?",
type=str,
default="/tmp/",
help=
"location to store the alignment .csv output file; Default= '/tmp/' ",
)
parser.add_argument(
"-m",
action="store",
nargs="?",
const=1,
type=float,
default=2.5,
help=
"Retention time tolerance value between compared peaks; Default=2.5",
dest="mod",
)
parser.add_argument(
"-m2",
action="store",
nargs="?",
const=1,
type=float,
default=2.5,
help=
"*Between-state: 2nd Retention time tolerance value between compared peaks; Default=2.5",
dest="mod2",
)
parser.add_argument(
"-g",
action="store",
nargs="?",
const=1,
type=float,
default=0.30,
help="Gap penalty for a non-aligning peak; Default=0.30",
dest="gap",
)
parser.add_argument(
"-g2",
action="store",
nargs="?",
const=1,
type=float,
default=0.30,
help=
"*Between-state: 2nd gap penalty for a non-aligning peak; Default=0.30",
dest="gap2",
)
parser.add_argument(
"-p",
action="store",
nargs="?",
const=1,
type=int,
default=2,
help=
"Minimum number of peaks per sample required for alignment; Default=2",
dest="minPeak",
)
parser.add_argument(
"-p2",
action="store",
nargs="?",
const=1,
type=int,
default=2,
help=
"*Between-state: 2nd minimum number of peaks pre sample required for alignment; Default=2",
dest="minPeak2")
parser.add_argument(
"-n",
action="store",
nargs="?",
type=str,
default="alignment-",
help=
"Identifier string used for .csv file storage; Default='alignment-'",
dest="nameTag")
parser.add_argument(
"-as",
choices=['inner', 'between'],
type=str,
default="inner",
help=
"Alignment strategies: inner-state, between-state; Default='inner' ",
dest='alignS')
args = parser.parse_args()
print(args)
list_of_exprs, names = glob(glob_pattern='*.expr',
directoryname=args.exprDir)
if args.alignS == "inner":
print('Singular alignment run')
expr_loaded = []
for i in list_of_exprs:
# print(i)
expr = load_expr(i)
expr_loaded.append(expr)
singleAlign(expr_loaded, args.opDir, args.mod, args.gap, args.minPeak,
args.nameTag)
print('Done!')
elif args.alignS == "between":
print('Between-state alignment run')
berries, name = rep_dict(list_of_exprs)
# print("berries=", berries)
# print("names", name)
repAlign(berries, args.opDir, args.mod, args.mod2, args.gap, args.gap2,
args.minPeak, args.minPeak2, args.nameTag)
print('Done!')
